Intelligent diagnosis of retinal vein occlusion based on color fundus photographs

AIM:To develop an artificial intelligence(AI)diagnosis model based on deep learning(DL)algorithm to diagnose different types of retinal vein occlusion(RVO)by recognizing color fundus photographs(CFPs).METHODS:Totally 914 CFPs of healthy people and patients with RVO were collected as experimental data sets,and used to train,verify and test the diagnostic model of RVO.All the images were divided into four categories[normal,central retinal vein occlusion(CRVO),branch retinal vein occlusion(BRVO),and macular retinal vein occlusion(MRVO)]by three fundus disease experts.Swin Transformer was used to build the RVO diagnosis model,and different types of RVO diagnosis experiments were conducted.The model’s performance was compared to that of the experts.RESULTS:The accuracy of the model in the diagnosis of normal,CRVO,BRVO,and MRVO reached 1.000,0.978,0.957,and 0.978;the specificity reached 1.000,0.986,0.982,and 0.976;the sensitivity reached 1.000,0.955,0.917,and 1.000;the F1-Sore reached 1.000,0.9550.943,and 0.887 respectively.In addition,the area under curve of normal,CRVO,BRVO,and MRVO diagnosed by the diagnostic model were 1.000,0.900,0.959 and 0.970,respectively.The diagnostic results were highly consistent with those of fundus disease experts,and the diagnostic performance was superior.CONCLUSION:The diagnostic model developed in this study can well diagnose different types of RVO,effectively relieve the work pressure of clinicians,and provide help for the follow-up clinical diagnosis and treatment of RVO patients.

Dexamethasone implant for refractory macular edema secondary to diabetic retinopathy and retinal vein occlusion

AIM:To evaluate the efficacy,timing of retreatment and safety of dexamethasone(DEX)implant on macular edema(ME)secondary to diabetic retinopathy(DME)and retinal vein occlusion(RVO-ME)patients who were refractory to anti-vascular endothelial growth factor(VEGF)treatment.METHODS:This retrospective study included 37 eyes received at least one DEX implant treatment for DME or RVO-ME between January 1,2019,and January 1,2023.These refractory DME and RVO-ME cases received at least 5 anti-VEGF injections and failure to gain more than 5 letters or a significant reduction in central retinal thickness(CRT).The best corrected visual acuity(BCVA)and CRT were measured at baseline,and at 1,3,4 and 6mo post-DEX implant injection.Adverse events such as elevated intraocular pressure(IOP)and cataract were recorded.RESULTS:For RVO cases(n=22),there was a significant increase in BCVA from 0.27±0.19 to 0.35±0.20 at 6mo post-DEX injection(P<0.05)and CRT decreased from 472.1±90.6 to 240.5±39.0μm at 6mo(P<0.0001).DME cases(n=15)experienced an improvement in BCVA from 0.26±0.15 to 0.43±0.20 at 6mo post-DEX implant injection(P=0.0098),with CRT reducing from 445.7±55.7 to 271.7±34.1μm at 6mo(P<0.0001).Elevated IOP occurred in 45.9% of patients but was well-controlled with topical medications.No cases of cataract or other adverse events were reported.CONCLUSION:DEX implants effectively improve BCVA and reduce CRT in refractory DME and RVO-ME.Further research with larger cohorts and longer follow-up periods is needed to confirm these findings and assess long-term outcomes.

Comparative Quantitative Analysis of Retinal Superficial Capillary Plexus in Patients with Retinal Vein Occlusion and Unaffected Fellow Eyes

Purpose: To evaluate optical coherence tomography angiography (OCT-A) data obtained from the superficial retinal capillary plexus of patients with retinal vein occlusion and comparative analysis with data registered from unaffected fellow eyes. Methods: The examined patients were classified into 2 groups: group 1—eyes with established retinal vein occlusion (n = 29) and group 2—unaffected fellow eyes of patients with retinal vein occlusion (n = 24). The scanning protocol “Angiography 3 × 3 mm” of Zeiss Cirrus HD-OCT 6000, AngioPlex Metrix was used to evaluate the retinal superficial capillary plexus. The analyzed parameters were vascular density and perfusion density, as well as the area, perimeter, and circularity of the foveolar avascular zone (FAZ). Results: The comparative analysis of FAZ parameters at the superficial capillary plexus (SCP) between group 1 (eyes with retinal vein occlusion) and group 2 (unaffected fellow eyes) showed significant results for the three parameters, respectively area (p = 0.003), perimeter (p ≤ 0.001), and circularity (p = 0.011) of FAZ. The comparative analysis of the vascular network at SCP in patients with diagnosed retinal vein occlusion and unaffected fellow eyes showed significant results for vascular density (VD) in the central (p = 0.038) and inner (p ≤ 0.001) zones as well as total VD (p ≤ 0.001) were statistically significant. Moreover, the results obtained in the study of vascular perfusion (VP) indicated significant results in the inner zone (p ≤ 0.001) and total VP (p = 0.001). Vascular perfusion in the central zone (p = 0.116) was the only parameter not to meet significant results. Conclusion: The current study observed a significant enlargement of the FAZ and loss of its circularity, along with a reduction in vascular network parameters at the superficial retinal capillary plexus level.

Pathogenesis, prevention, diagnosis and management of retinal vein occlusion

Retinal vein occlusion(RVO) is the second vascular retinal cause of visual loss and defined by the occlusion of a retinal vein. It is divided into branch retinal vein occlusion or central retinal vein occlusion, depending on the location of occlusion. RVO has severe medical, financial and social implications on the patients. The diagnosis of the disease is easier nowadays with the use of spectral domain optical coherence tomography and fluorescein angiography. The treatment options for RVO have changed dramatically over the past few years with the introduction of the intravitreal injections of dexamethasone(Ozurdex), bevacizumab(Avastin), ranibizumab(Lucentis) and aflibercept(EYLEA), along with the panretinal laser photocoagulation, abandoning former treatment modalities and surgical solution. This manuscript is a review of current literature about RVO with emphasize on the pathophysiology, risk factors and prevention, diagnosis and sub-group categorization and treatments including medical and surgical. Since no official guidelines are available for the treatment of RVO patients, and considering the latest developments in the treatment options, and the variety of follow-up and treatment modalities, this manuscript aims to provide tools and knowledge to guide the physician in treating RVO patients, based on the latest publications from the literature and on several of the patients characteristics.

Intravitreal injection of bevacizumab alone or with triamcinolone acetonide for treatment of macular edema caused by central retinal vein occlusion

AIM: To compare the efficacy and safety of intravitreal bevacizumab alone versus bevacizumab combined with triamcinolone acetonide in eyes with macular edema caused by central retinal vein occlusion (CRVO) in Chinese patients. METHODS: Seventy-five eyes of 75 patients were enrolled in this prospective, randomized, consecutive study. Thirty-six patients in group 1 were treated with an intravitreal injection of bevacizumab (1.25mg/0.05mL), and 39 patients in group 2 were treated with intravitreal bevacizumab (1.25mg/0.05mL) combined with triamcinolone acetonide (2mg/0.05mL). The main outcomes of the mean best corrected visual acuity (BCVA), central retinal thickness (CRT), and intraocular pressure (IOP) were measured. RESULTS: In group 1, the mean BCVA improved from 37.78 +/- 6.14 (baseline) to 48.06 +/- 3.86, 46.48 +/- 4.77 and 44.18 +/- 5.78 at four, six and twelve weeks post-injection, respectively (P<0.01, P=0.03, P=0.04). In group 2, the mean BCVA improved from 35.92 +/- 6.20 (baseline) to 50.69 +/- 4.22, 48.76 +/- 5.59 and 45.70 +/- 6.56 at the same time points (P<0.01 each). However, there was no significant differences in the mean BCVA (F=0.043, P=0.836) and CRT (F=0.374, P=0.544) between these two groups. During the follow-up, five patients in group 1 and six patients in group 2 with high IOP were controlled with anti-glaucoma drugs. CONCLUSION: Intravitreal injection of bevacizumab alone or combined with triamcinolone acetonide has a short beneficial effect in Chinese patients with macular edema caused by CRVO, but there is no significant difference between the two groups.

Comparison of intravitreal bevacizumab with intravitreal triamcinolone acetonide for treatment of cystoid macular edema secondary to retinal vein occlusion : a Meta-analysis

AIMTo compare the effects of intravitreal injection of bevacizumab (IVB) with intravitreal triamcinolone acetonide (IVTA) on the treatment of cystoid macular edema (CME) secondary to retinal vein occlusion (RVO).METHODSA literature search was conducted using PubMed, the Cochrane Central Register of Controlled Trials, Web of Science and the Chinese Biomedical Database. The comparison was divided into two groups, group 1 conducted comparison in branch RVO (BRVO) or central RVO (CRVO), group 2 conducted comparison in ischemic-RVO or nonischemic-RVO. Pooled mean differences (MDs) for changes in visual acuity (VA), central macular thickness (CMT) and intraocular pressure (IOP) were calculated in groups at 4, 12 and 24wk after treatment respectively.RESULTSEight studies comparing the efficacy of IVB with IVTA were included in the Meta-analysis. In group 1, in BRVO, significant difference was shown on the comparison of CMT at 24wk (MD, -45.66; 95% CI, -76.03 to -15.28; P=0.003), IVB was effective on BRVO for at least 24wk; no significant differences were found in the comparison of VA at each time points (P&#x0003e;0.05 respectively). In CRVO, no significant differences were found in the comparison of VA or CMT between IVB and IVTA at each time points (P&#x0003e;0.05, respectively). In group 2, in ischemic-RVO, significant differences were shown in the comparison of VA (MD, -0.28; 95% CI, -0.42 to -0.14; P&#x0003c;0.0001) and CMT (MD, -86.50; 95% CI, -151.18 to -22.43; P=0.008) at 24wk; In nonischemic-RVO, no significant differences were demonstrated in the comparison of VA or CMT between IVB and IVTA at each time points (P&#x0003e;0.05, respectively). The occurrence of high IOP was much lower in IVB group.CONCLUSIONThis Meta-analysis suggested that IVB was effective in decreasing CMT in BRVO for at least 24wk, IVB is more effective on improving VA and reducing CMT in ischemic-RVO. IVB is more promising on RVO than IVTA.

Comparison of intravitreal ranibizumab and bevacizumab for the treatment of macular edema secondary to retinal vein occlusion

AIMTo compare the efficacy of ranibizumab and bevacizumab for macular edema due to retinal vein occlusion (RVO).

Comparison of efficacy of conbercept,aflibercept,and ranibizumab ophthalmic injection in the treatment of macular edema caused by retinal vein occlusion:a Meta-analysis

AIM:To evaluate and compare the anatomical and functional outcomes and negative effects of the three anti-vascular endothelial growth factor(VEGF)drugs in the treatment of macular edema(ME)due to retinal vein occlusion(RVO)based on the evidence pooled from current clinical trials and observational studies.METHODS:A systematic literature search was conducted on nine online databases from inception until April 30,2022.The main endpoints were best corrected visual acuity(BCVA),central macular thickness(CMT),and adverse events(AEs).Cumulative Meta-analysis was conducted to synthesize the outcomes of the drugs.The retrieved data were analyzed using Stata software(version 12.0).RESULTS:A total of 20 studies comprising 1674 eyes met the inclusion criteria to the Meta-analysis.It was observed that conbercept and aflibercept had better visual acuity effects compared with ranibizumab at 1mo[weight mean difference(WMD)=-0.03,P=0.001;WMD=-0.05,P=0.019],but the effects were not different from that of ranibizumab at 6mo.Moreover,there was not statistically significant dif ference in the propor tion of patients gaining≥15 letters at 12-24mo between aflibercept and ranibizumab[odds ratio(OR)=1.16,P=0.427].Conbercept had higher mean CMT change effects at 1mo(WMD=-14.43,P=0.014)and 6mo(WMD=-35.63,P≤0.001)compared with ranibizumab.Meanwhile,the mean CMT change effects at 1mo(WMD=-10.14,P=0.170),6mo(WMD=-26.98,P=0.140)and 12-24mo(WMD=-12.34,P=0.071)were comparable among the groups.Similarly,AEs were not significantly different among the treatments(OR=0.75,P=0.305;OR=1.04,P=0.89).The stability of effect size of mean BCVA and CMT improved with the increase in sample size.Aflibercept and conbercept required fewer injections compared with ranibizumab.CONCLUSION:This is the first study to evaluate the efficacy and AEs of intravitreal administration of conbercept,ranibizumab,and aflibercept in the treatment of RVOME.Intravitreal aflibercept or conbercept results in better mean change in vision and CMT reduction compared with ranibizumab.Conbercept can be considered to be a promising and innovative drug with good anti-VEGF effects.

Peripheral retinal non-perfusion and treatment response in branch retinal vein occlusion

AIM： To evaluate the association between the size of peripheral retinal non-perfusion and the number of intravitreal ranibizumab injections in patients with treatment-naive branch retinal vein occlusion （BRVO） and macular edema. METHODS： A total of 53 patients with treatment-naive BRVO and macular edema were included. Each patient underwent a full ophthalmologic examination including optical coherence tomography （OCT） imaging and ultra wide-field fluorescein angiography （UWFA）. Monthly intravitreal ranibizumab injections were applied according to the recommendations of the German Ophthalmological Society. Two independent, masked graders quantified the areas of peripheral retinal non-perfusion. RESULTS： Intravitreal injections improved bestcorrected visual acuity （BCVA） significantly from 22.23± 16.33 Early Treatment of Diabetic Retinopathy Study （ETDRS） letters to 36.23 ±15.19 letters （P〈0.001）, and mean central subfield thickness significantly reduced from 387±115 pm to 321±115 μm （P=0.01）. Mean number of intravitreal ranibizumab injections was 3.61±1.56. The size of retinal non-perfusion correlated significantly with the number of intravitreal ranibizumab injections （R= 0.724, P〈0.001）. CONCLUSION： Peripheral retinal non-perfusion in patients with BRVO associates significantly with intravitreal ranibizumab injections in patients with BRVO and macular edema.

Visual acuity after intravitreal ranibizumab with and without laser therapy in the treatment of macular edema due to branch retinal vein occlusion:a 12-month retrospective analysis

AIM:To identify factors contributing to visual improvement after treatment of macular edema(ME)secondary to branch retinal vein occlusion(BRVO),and to assess the interaction between laser therapy and intravitreal ranibizumab(IVR).METHODS:We retrospectively reviewed the medical records of patients who had been treated for BRVO-related ME at our hospital.Records were traceable for at least 12 mo,and evaluated factors included age,sex,medical history,smoking history,treatment methods,foveal hemorrhage,and change in visual acuity.Treatments included laser therapy,IVR,sub-Tenon’s capsule injection of triamcinolone(STTA),a combination,or no intervention.Multivariate logistic regression analysis and interaction terms were used to assess the clinical efficacy of the treatments,and odds ratios(OR)and 95%confidence intervals(CI)were calculated.RESULTS:Seventy-three patients(34 men,39 women;73 eyes)with a mean age of 69.4±12.1 y were included.Patients who underwent IVR monotherapy,laser monotherapy,and STTA+laser had significantly higher best corrected visual acuity at 12 mo compared to baseline(P<0.001,<0.001,and 0.019,respectively).Logistic regression analysis without interaction terms found that IVR was a significant visual acuity recovery factor(adjusted OR:3.89,95%CI:1.25-12.1,P=0.019).Adjusted OR using an interaction model by logistic regression was 16.6(95%CI:2.54-108.47,P=0.003)with IVR treatment,and 8.25(95%CI:1.34-50.57,P=0.023)with laser treatment.No interaction was observed(adjusted OR:0.07,95%CI:0.01-0.75,P=0.029).CONCLUSION:IVR contributes to improvements in visual acuity at 12 mo in ME secondary to BRVO.No interaction is observed between laser therapy and IVR treatments.

Long-term outcomes of anti-VEGF treatment with 5+PRN regimen for macular edema due to central retinal vein occlusion

AIM:To assess the long-term outcomes of treating macular edema(ME)associated with central retinal vein occlusion(CRVO)with a regimen of“5+pro re nata(PRN)”.METHODS:This retrospective study included 27 eyes of 27 patients with ME associated with non-ischemic CRVO(non-iCRVO group,n=15)and ischemic CRVO(iCRVO group,n=12).The eyes were treated with five consecutive intravitreal injections of conbercept or ranibizumab,followed by reinjections as needed or PRN.Retinal laser photocoagulation or intravitreal dexamethasone implants(DEX)were implemented in both groups when necessary.The best-corrected visual acuity(BCVA,logMAR)and central retinal thickness(CRT)were recorded at baseline,at 1,2,3,4,5,6,and 12mo,and at the final visit.The efficacy rates of BCVA and CRT before and after treatment were calculated.The number of injections at each visit and the incidence of adverse events were also recorded.RESULTS:The patients,aged 59.4±15.1y,were followed up for 24.7±8.8mo(range:15-42mo).After treatment,BCVA improved significantly from 1.04±0.56 logMAR at baseline to 0.59±0.36 logMAR(P=0.038)at the final visit in all patients.Both the non-iCRVO and the iCRVO groups achieved improved BCVA compared to the baseline at all visit points,but there was no statistical significance(P=0.197 and 0.33,respectively).The mean CRT was statistically reduced compared to baseline at all visit points in all the eyes and in both groups(all P<0.001).The apparent effective rate was 22.22% for BCVA and 37.04% for CRT after the first injection,48.15%for BCVA and 62.96% for CRT after 5 consecutive injections,and 74.08% for BCVA and 100% for CRT at the end of follow up.The average number of injections in all patients was 9.0±2.4 at 12mo and 14.9±8.1 finally with no statistical significance between both groups(P>0.05).Laser treatment was applied to all eyes in the iCRVO group,while only 5 patients in the noniCRVO group.Six patients in the non-iCRVO group and 3 patients in the iCRVO group had a drug switch.DEX was applied to 4 eyes in the non-iCRVO group and 5 eyes in the iCRVO group.CONCLUSION:The 5+PRN anti-vascular endothelial growth factor(VEGF)regimen is found to be safe and effective for both iCRVO and non-iCRVO,especially in the iCRVO group.The best regimen for such patients needs to be further investigated.Adjuvant laser therapy and DEX are necessary in some cases.

Artificial intelligence can assist with diagnosing retinal vein occlusion

AIM:To assist with retinal vein occlusion(RVO)screening,artificial intelligence(AI)methods based on deep learning(DL)have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible.METHODS:A total of 8600 color fundus photographs(CFPs)were included for training,validation,and testing of disease recognition models and lesion segmentation models.Four disease recognition and four lesion segmentation models were established and compared.Finally,one disease recognition model and one lesion segmentation model were selected as superior.Additionally,224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models.RESULTS:Using the Inception-v3 model for disease identification,the mean sensitivity,specificity,and F1 for the three disease types and normal CFPs were 0.93,0.99,and 0.95,respectively,and the mean area under the curve(AUC)was 0.99.Using the DeepLab-v3 model for lesion segmentation,the mean sensitivity,specificity,and F1 for four lesion types(abnormally dilated and tortuous blood vessels,cotton-wool spots,flame-shaped hemorrhages,and hard exudates)were 0.74,0.97,and 0.83,respectively.CONCLUSION:DL models show good performance when recognizing RVO and identifying lesions using CFPs.Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists,DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.

Treatment Options of Macular Edema Secondary to Retinal Vein Occlusion (RVO): A Review

Retinal Vein Occlusion (RVO) is a common retinal vascular disease secondary to diabetic retinopathy resulting in permanent loss of vision despite available treatment options. Main vision impending complication of retinal vein occlusion is macular edema. Laser photocoagulation has been an established method for treating macular edema for many years but nowadays intravitreal injection of Anti-Vascular endothelial growth factors (Ranibizumab, Aflibercept Bevacizumab and Pegaptanib sodium) is the treatment of choice for macular edema from retinal vein occlusion. Intra-vitreal corticosteroids Triamcinolone Acetonide and Dexamethasone implant, are also being used to treat in some macular edema cases but with higher rates of side effects. Numerous surgical methods have been attempted for treating RVO and preventing macular edema;they include pars plana vitrectomy, radial optic neurotomy, laser induced chorioretinal anastomosis, and arteriovenous sheathotomy. Surgical methods supposedly relieve compression of the central retinal vein, altering the pathophysiology of vein occlusion at the level of the lamina cribrosa thus improving blood flow and oxygenation. But limitations result from its complications.

Preliminary Clinical Observation of Arteriovenous Sheathotomy for Treatment of Branch Retinal Vein Occlusion

Purpose: To document the anatomic and functional improvement of six patients withbranch retinal vein occlusion (BRVO) following successful arteriovenous adventitialsheathotomy (AAS).Methods: Retrospective study of 6 patients (6 eyes) with BRVO treated with AAS. Allpatients were not eligible for laser photocoagulation and had both macular edema andintraretinal hemorrhage. The visual acuity was in the range of 0.4 to 0.02. All patientsunderwent pars plana vitrectomy and AAS. The clinical improvement was determined byfundus photograph, fluorescein angiography (FAG), optical coherence tomography(OCT) and multifocal electroretinography (ERG). All patients were followedpostoperatively for an average of 20 months ranging from 12 to 24 months.Results: Sheathotomy and decompression of the arteriole/venule (A/V) crossing wereachieved in all 6 patients. 5 patients have improved their best-corrected visual acuity 4lines or more. The best one could reach to 1.0. One month after the operation, fundusphotograph and FAG demonstrated the resolution of intraretinal hemorrhage, reduction ofnon-perfusion area and apparent resolution of retinal venous dilation and tortuosity. OCTconfirmed remarkable reduction of retinal thickness. The microcysts at the foveadiminished. Multifocal ERG showed the recovery of the central peak at the macular andthe peripheral response density. However, capillary nonperfusion area andmicroaneurysm were found out by FAG in four patients at the points distal to thesheathotomy three months after the operation.Conclusions: Anatomic and functional improvement of retina can be achieved in patientswith BRV0 through AAS. However, the capillary nonperfusion and microaneurysm mayfollow this surgical procedure in some cases that need further treatment with laserphotocoagulation. The better visual improvement may be expected in the patients withearlier surgical intervention.

Treatment controversies in a rare case of a simultaneous branch retinal artery and vein occlusion secondary to hyperhomocysteinemia and hypertension

Dear Editor,Combined vascular occlusions involving retinal arteries and veins have been reported in the past. Combined occlusion of the central retinal vein （CRVO） and artery （CRAO）is well described;. Cilioretinal artery occlusion along with CRVO is frequently reported and is well characterized;.

Efficacy of intravitreal injection of ranibizumab in the treatment of macular edema secondary to non-ischemic branch retinal vein occlusion

Objective: To observe the efficacy of intravitreal injection of ranibizumab in the treatment of macular edema(ME) secondary to non-ischemic branch retinal vein occlusion (BRVO). Methods: The clinical data of 27 patients (27 eyes) with macular edema secondary to non-ischemic BRVO were diagnosed by ophthalmology in Chongqing University Center Hospital from May 2018 to April 2019, selected as the experimental group, and 20 cases (20 eyes) of normal people as the control group. For the experimental group, before and after treatment, 1wk, 1mo, 2mo, 3mo and 6mo were used to observe the uncorrected visual acuity(UCVA),best corrected visual acuity (BCVA), intraocular pressure (IOP), central retinal thickness (CRT) macular center volume (MCV) and EN FACE images. Subjects in the normal control group were examined by optical coherence tomography (OCT) for CRT and CMV at 1wk, 1mo, 2mo, 3mo and 6mo on the day of and after enrollment. Results: The mean age of patients in the experimental group was (67.37±8.63) years old and the times of Intravitreal injection was (3.26 ±0.59) times. The successful rate of treatment was 85.19%. There was no significant difference in IOP between pre-treatment and 1wk, 1mo, 2mo, 3mo and 6mo (P > 0.05). 1wk, 1mo, 2mo, 3mo and 6mo BCVA were significantly higher than those before treatment (P < 0.0001). The levels of CRT and CMV at 1wk, 1mo, 2mo, 3mo and 6mo after treatment were significantly lower than those before treatment (P <0.01). Compared with the normal control group, the CRT and CMV of the experimental group before and after treatment showed statistically significant differences in 1wk, 1mo, 2mo and 3mo (P <0.05). There was no statistically significant difference in 6mo CRT and CMV after treatment (P>0.05). EN FACE showed that 1wk, 1mo, 2mo, 3mo and 6mo macular thickness decreased gradually, retinal edema subsided, cystoid changes disappeared, and the interlamellar structure of the ellipsoid zone gradually recovered after intravitreal injection of ranibizumab. Conclusion: Intravitreal injection of ranibizumab in the treatment of non-ischemic BRVO secondary ME has significant efficacy, EN FACE is an effective means to assess the severity, treatment and prognosis of patients.

The Modality of Huoxue-Huayuin Treatment of Retinal Vein Occlusion

Background:There were some reports in China about Huoxue-Huayu therapy on retinal vein occlusion(RVO),but prospective and systematic studies are very few.The curative effect and mechanism of this therapy on RVO have not been re-ported Previously6.Methods:80patients with RVO were randomly divided into2groups,FundusⅢ（groupA)and urokinase group(groupB).GroupAwas treated by FundusⅢo-ral liquid(a composite herbal recipe for Huoxue-Huayu or invigoration of blood circulation and reduction of blood stasis)10ml/timeP.O.t.i.d,The treatment course was1 mouth,Group Bwas treated by urokinase.The urokinase that pro-duced in China was used 10000u+5%glucose 500ml/dayi.v.drip for 5days in a course,the rest 5days going on another course.The total treatment courses last-ed 1month.too.Results:The visual acuity in group A was remarkably improved while that in group B did not change.The extravasated retinal blood was evidently absorded in 92.7%fo the cases in group Aand in 66.7%of those in groupB.Thedifference was significant.FundusⅢalso improved the retinal circulation.Decreased the whole blood viscosity and fibrinogen and educed leakage of the retinal capillar-ies.THe total effective rates were83.7%in group Aand58.7%in group Bwith significant statistical difference between the 2groups(P<0.01).Conclusion:FundusⅢmay alleviate retinal edema and necroses,improve the re-covering of visual acuity,the retinal microcirculation,th rate of absorbing of reti-nal haemorrhage and treat RVO,and the curative effect is better than urokinase.

Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion

AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field fundus images. METHODS: This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6 y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4 y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value(PPV), negative predictive value(NPV) and area under the curve(AUC) were calculated to compare the diagnostic abilities of the DL and SVM models. RESULTS: For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0%(95%CI: 93.8%-98.8%), 97.0%(95%CI: 89.7%-96.4%), 96.5%(95%CI: 94.3%-98.7%), 93.2%(95%CI: 90.5%-96.0%) and 0.976(95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5%(95%CI: 77.8%-87.9%), 84.3%(95%CI: 75.8%-86.1%), 83.5%(95%CI: 78.4%-88.6%), 75.2%(95%CI: 72.1%-78.3%) and 0.857(95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters(P<0.001). CONCLUSION: These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center.

Microvascular changes after conbercept therapy in central retinal vein occlusion analyzed by optical coherence tomography angiography

AIM: To investigate microvascular changes in eyes with central retinal vein occlusion(CRVO) complicated by macular edema before and after intravitreal conbercept injection and evaluate correlations between these changes and best-corrected visual acuity(BCVA) and retinal thickness. METHODS: Twenty-eight eyes of 28 patients with macular edema caused by CRVO were included in this retrospective study. All patients received a single intravitreal conbercept injection to treat macular edema. BCVA and the results of optical coherence tomography angiography(OCTA) automatic measurements of the vessel density in the superficial(SCP) and deep retinal capillary plexus(DCP), the foveal avascular zone(FAZ) area, the FAZ perimeter(PERIM), the vessel density within a 300-μm wide ring surrounding the FAZ(FD-300), the acircularity index(AI), the choriocapillaris flow area, and retinal thickness were recorded before and at one month after treatment and compared with the results observed in age-and sexmatched healthy subjects. RESULTS: The vessel density in the SCP and DCP, the FD-300, and the flow area of the choriocapillaris were allsignificantly lower in CRVO eyes than in healthy eyes, while the AI and retinal thickness were significantly higher(all P<0.05). After treatment, retinal thickness was significantly decreased, and the mean BCVA had markedly improved from 20/167 to 20/65(P=0.0092). The flow area of the choriocapillaris was also significantly improved, which may result from the reduction of shadowing effect caused by the attenuation of macular edema. However, there were no significant changes in SCP and DCP vessel density after treatment. The flow area of the choriocapillaris at baseline was negatively correlated with retinal thickness.CONCLUSION: OCTA enables the non-invasive, layerspecific and quantitative assessment of microvascular changes both before and after treatment, and can therefore be used as a valuable imaging tool for the evaluation of the follow-up in CRVO patients.

Therapeutic potential of intravitreal pharmacotherapy in retinal vein occlusion

Retinal vein occlusion (RVO) is the most common visually disabling disease affecting the retina after diabetic retinopathy. Although the disease entity has long been known, its management is still controversial. Macular edema is the main reason for decreased visual acuity (VA) in this retinal vascular disorder. Recently the vitreous cavity has increasingly been used as a reservoir of drugs for the direct treatment of macular edema through intravitreal injection route. The most widely injected drugs so far have been triamcinolone acetonide (TA) and bevacizumab. The objective of this review is to evaluate the evidence and discuss the rationale behind the recent suggestions that intravitreal pharmacotherapy by corticosteroids and anti-vascular endothelial growth factors may be useful in the treatment of retinal vein occlusion.